Artificial ventriloquist-like contact center agents
The need for efficient and effective communications is of key importance to contact centers. Agent communications with customers are designed to maximize results while minimizing resources, in particular the time required for human agents to be engaged with a particular customer. Often the impact of two agents on a communication can both improve customer satisfaction and better produce the intended result of the communication. However, two (or more) live agents is resource intensive. By providing a virtual agent controlled, entirely or in part, by a live agent, the customer may be presented with the appearance of two agents while requiring the human resources of a single agent.
1. A system, comprising:
a communication interface to a network;
a processor comprising machine-readable instructions maintained in a non-transitory memory;
a first agent communication device comprising an input device and a microphone and utilized by a live agent;
a data storage; and
wherein a first agent, via the first agent communication device, is engaged in a communication with a customer, utilizing a customer communication device, and wherein the communication comprises speech encoded for transmission on the network; and
wherein the instructions cause the processor to perform:
accessing an agent persona, from the data storage, comprising settings of characteristics to generate speech of a virtual agent different from the speech of the first agent and wherein the agent persona further comprises settings to generate a video image of the virtual agent having visual characteristics different from an image of the first agent;
receiving content, via the input device;
generating speech of the content in a voice of the agent persona;
providing the generated speech as a portion of the communication; and
providing the video image of the virtual agent as a video portion of the communication.
2. The system of claim 1 , wherein the input device comprises a keyboard and the processor performs generating the speech from text entered via the keyboard.
3. The system of claim 1 , wherein the instructions cause the processor to further receive a signal sent from the input device and, in response, receive the content as speech from the microphone, block the speech of the first agent from being provided to the customer communication device, and generate the speech comprising converting the speech of the first agent to a voice of the virtual agent and providing the voice of the virtual agent to the communication.
4. The system of claim 1 , further comprising:
a camera receiving a video image of the first agent, wherein the image is encoded for transmission on the network; and
wherein the instructions cause the processor to provide as the video image of the virtual agent in the communication, the video image of the virtual agent with a characteristic of the first agent in a video image of the first agent while maintaining a visual appearance of the virtual agent as distinct from the first agent.
5. The system of claim 4 , wherein the characteristic comprises at least one of gesture, clothing, facial expression, or pattern of speech.
6. The system of claim 1 , wherein the instructions further cause the processor to perform:
receiving a signal sent from the input device and, in response thereto, further receiving the content as speech from the microphone, blocking a video image of the first agent's face, comprising at least a mouth portion, with an overlay to present a video image of the first agent as not speaking while the video image of the virtual agent is speaking.
7. The system of claim 6 , wherein the instructions cause the processor to animate the video image of the virtual agent's face, comprising at least the mouth portion, to mimic facial movements of the first agent while the first agent speaks.
8. The system of claim 1 , wherein the system further comprises:
a second agent communication device utilized by a second agent; and
wherein the instructions further cause the processor to receive a signal sent from at least one of the first agent communication device and the second agent communication device and, in response thereto, discontinue receiving the content from the first agent communication device and receives content from the second agent communication device.
9. The system of claim 8 , wherein the agent persona substantially matches a persona of the second agent.
10. A method, comprising:
engaging in a communication between a customer, utilizing a customer communication device connected to a network, and a first agent, utilizing a first agent communication device connected to a network, and wherein the communication comprises speech encoded for transmission on the network;
accessing an agent persona, from a data storage, comprising settings of characteristics to generate speech of a virtual agent different from the speech of the first agent and generating a video image of the virtual agent having visual characteristics different from an image of the first agent;
receiving content, via an input device associated with the first agent communication device;
generating speech of the content in a voice of the agent persona;
providing the generated speech as a portion of the communication; and
providing the video image of the virtual agent as a video portion of the communication.
11. The method of claim 10 , wherein the input device comprises a keyboard and generating speech comprises generating speech from text entered via the keyboard.
12. The method of claim 10 , further comprising:
receiving a signal sent from the input device and, in response, receiving the content as speech from a microphone capturing sound from the first agent, blocking the speech of the first agent from being provided to the customer communication device, and generating the speech comprising converting the speech of the first agent into a voice of the virtual agent; and
providing the voice of the virtual agent to the communication.
13. The method of claim 10 , further comprising:
receiving a video image of the first agent from a camera capturing an image of the first agent, wherein the image is encoded for transmission on the network; and
providing the video image of the virtual agent in the communication, the video image of the virtual agent having characteristics of the first agent in the video image of the first agent while maintaining a visual appearance of the virtual agent as distinct from the first agent.
14. The method of claim 13 , wherein the characteristics comprise at least one of gesture, clothing, facial expression, or pattern of speech.
15. The method of claim 10 , further comprising receiving a signal sent from the input device and, in response thereto, further receiving the content as speech from a microphone, blocking a video image of the first agent's face, comprising at least a mouth portion, with an overlay to present the image of the first agent as not speaking while the video image of the virtual agent is speaking.
16. The method of claim 15 , wherein further comprising animating the video image of the virtual agent's face, comprising at least the mouth portion, to mimic facial movements of the first agent while the first agent speaks.
17. The method of claim 10 , further comprising:
receiving a signal sent from at least one of the first agent communication device and a second agent communication device and, in response thereto, discontinuing receiving the content from the first agent communication device and receiving content from the second agent communication device.
18. An agent communication device for communicating, via a network with a customer communication device, comprising:
a communication interface to the network;
a processor, comprising machine-readable instructions maintained in a non-transitory memory;
a microphone capturing speech of an agent;
a camera capturing a video image of the agent;
a data storage; and
wherein the agent, utilizing the agent communication device, is engaged in a communication with a customer, utilizing the customer communication device, and wherein the communication comprises speech encoded for transmission on the network; and
wherein the instructions cause the processor to perform:
accessing a virtual agent persona, from the data storage, comprising settings of characteristics to generate a virtual agent different from the agent;
generating the virtual agent to comprise speech of the agent and having a voice of the virtual agent persona;
generating a video image of the virtual agent having at least a movement as determined by a movement of the agent as captured in the video image of the virtual agent;
generating an altered video image of the agent having an appearance of not speaking while the video image of the virtual agent is speaking;
providing, as a portion of the communication, the video image of the virtual agent, the altered video image of the agent, and speech in the voice of the virtual agent persona; and
providing a generated speech as a portion of the communication.
19. The agent communication device of claim 18 , wherein the instructions cause the processor to further receive a signal sent from the agent communication device and, in response, receive a portion of the communication as speech from the microphone, blocking the speech of the agent from being provided to the customer communication device, and generating the speech comprising converting the speech of the agent to a voice of the virtual agent and providing speech the voice of the virtual agent to the communication.
20. The agent communication device of claim 18 , wherein the instructions further cause the processor to perform receiving a signal sent from the agent communication device and, in response thereto, further receiving a portion of the communication as speech from the microphone, blocking a video image of the agent's face, comprising at least a mouth portion, with an overlay to present an image of the agent as not speaking while the video image of the virtual agent is speaking.